Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    meetings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    esteps
    -0.08
     OL
    -0.08
     Duel
    -0.08
    ).↵
    -0.07
     Eiffel
    -0.07
     parado
    -0.07
     Soft
    -0.07
     eventual
    -0.07
    ρισ
    -0.07
     Sequence
    -0.07
    POSITIVE LOGITS
    讨论
    0.11
     обс
    0.11
    Discuss
    0.10
     bespreken
    0.10
     discuter
    0.10
     gemeinsam
    0.10
     collaboratively
    0.09
     discutir
    0.09
     discussing
    0.09
    Reconnect
    0.08
    Act Density 0.179%

    No Known Activations